aria2 is a lightweight multi-protocol & multi-source, cross platform download utility operated in command-line. It supports HTTP/HTTPS, FTP, SFTP, BitTorrent and Metalink.

ModelScope: bring the notion of Model-as-a-Service to life.

Reason bindings for ReactJS

Speech-to-text, text-to-speech, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 serve…

Free, Open Source, Lightweight, Cross-platform Software for Royal Kludge Keyboards

日本語LLMまとめ - Overview of Japanese LLMs

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Vim python-mode. PyLint, Rope, Pydoc, breakpoints from box.

The official Python library for the OpenAI API

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

kakasi is a Rust library to transliterate hiragana, katakana and kanji (Japanese text) into rōmaji (Latin/Roman alphabet)

全国書誌データから作成した振り仮名のデータセット

Linguistic tools for texts in Japanese language

Javascript library for detecting and transforming between Hiragana, Katakana, and Romaji

Adds furigana to Japanese kanji.

Python tools for WhisperKit: Model conversion, optimization and evaluation

On-device Inference of Whisper Speech Recognition Models for Apple Silicon

whisper swiftui realtime demo using whisper.cpp

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Python wrapper for OpenJTalk

Massive open Japanese speech corpus

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合中国宝宝的部署教程

LPIPS metric. pip install lpips

ConvMAE: Masked Convolution Meets Masked Autoencoders

[WACV 2024] Code for "Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders"

[AAAI2024] FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning

The research collection of typography